Elamur Research
☰
home / papers / 2013 / The perfect solution for detecting sarcasm in tweets \#not

The perfect solution for detecting sarcasm in tweets \#not

Written for the Research library (claude-opus-5-5) from the paper text, in our own words: the license "CC BY-NC-SA 3.0 (ACL Anthology, before 2016)" does not allow redistributing the text itself. Original — aclanthology.org/W13-1605.pdf

Summary

Sarcasm can invert the polarity of a message, often by using positive or exaggerated wording to express a negative view, which undermines sentiment analysis. The authors build a sarcasm detector for Dutch Twitter. They use the author-supplied hashtag #sarcasme as a noisy label. They gathered 77,948 tagged tweets from a Netherlands e-Science Centre archive of Dutch tweets, and a manual check of a sample suggested about 85% are genuinely sarcastic. A machine learning classifier was trained on this data and evaluated on a realistic, heavily imbalanced test set: a full day of 3.3 million Dutch tweets. With the hashtag stripped, the classifier recovered three quarters of the explicitly tagged tweets. Among its highest-ranked untagged tweets, however, only about 30% were actually sarcastic, showing how difficult open-world detection is. A linguistic analysis found that sarcastic tweets are mostly literally positive and rely on intensifiers, exclamations or explicit markers. The authors argue that hashtags act as a written stand-in for the tone of voice and facial cues used in spoken sarcasm.

Key points

  • Training data: 77,948 Dutch tweets carrying #sarcasme. Annotation of a sample indicated roughly 85% are truly sarcastic.
  • Test set: one day's stream of 3.3 million Dutch tweets, of which only 135 carried the hashtag. With the tag removed, the classifier found 101 of them (75%).
  • Untagged tweets: precision in the top-250 ranked tweets was about 30%, with 76 tweets judged sarcastic.
  • Strongest predictors: positive intensifiers (e.g., geweldig, heerlijk, fantastisch) and plain positive words, with relatively few negative words.
  • Breakdown of the 76 sarcastic tweets:
    • 34.2% carried only an explicit marker and no hyperbole.
    • 59.2% contained intensifiers and/or exclamations.
    • Only 2.6% combined all three cue types.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Linguistics & languages

Cited by

51 papers of our library cite it (of the 140673 whose bibliographies we read); 14 of them have a page here, 37 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work.

@inproceedings{liebrecht2013perfect,
  title = {{The perfect solution for detecting sarcasm in tweets \#not}},
  author = {Liebrecht, Christine and Kunneman, Florian and Bosch, Antal van den},
  booktitle = {Proceedings of the 4th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis},
  year = {2013},
  url = {https://aclanthology.org/W13-1605/}
}

References

47 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. S. Attardo, J. Eisterhold, J. Hay, and I. Poggi. 2003. Visual markers of irony and sarcasm. Humor, 16(2):243–260. find
  2. S. Attardo. 2000. Irony as relevant inappropriateness. Journal of Pragmatics, 32(6):793–826. find
  3. S. Attardo. 2007. Irony as relevant inappropriateness. In R. W. Gibbs, R. W. Gibbs Jr., and H. Colston, editors, Irony in language and thought: A cognitive science reader, pages 135–170. Lawrence Erlbaum, New York, NY. find
  4. J. W. Bowers. 1964. Some correlates of language intensity. Quarterly Journal of Speech, 50(4):415–420, December. find
  5. R. L. Brown. 1980. The pragmatics of verbal irony. In R. W. Shuy and A. Shnukal, editors, Language use and the uses of language, pages 111–127. Georgetown University Press, Washington, DC. find
  6. G. A. Bryant and J. E. Fox Tree. 2005. Is there an ironic tone of voice? Language and Speech, 48(3):257–277. find
  7. C. Burfoot and T. Baldwin. 2009. Automatic satire detection: Are you having a laugh? In Proceedings of the ACL-IJCNLP 2009 Conference Short Papers, pages 161–164. Association for Computational Linguistics. find
  8. C. F. Burgers. 2010. Verbal irony: Use and effects in written discourse. Ipskamp, Nijmegen, The Netherlands. find
  9. H. S. Cheang and M. D. Pell. 2009. Acoustic markers of sarcasm in Cantonese and English. The Journal of the Acoustical Society of America, 126:1394. find
  10. T. Fawcett. 2004. ROC graphs: Notes and practical considerations for researchers. Technical Report HPL-2003-4, Hewlett Packard Labs. find
  11. R. W. Gibbs and H. Colston. 2007. Irony as persuasive communication. In R. W. Gibbs, R. W. Gibbs Jr., and H. Colston, editors, Irony in language and thougt: A cognitive science reader, pages 581–595. Lawrence Erlbaum, New York, NY. find
  12. R. W. Gibbs and C. Izett. 2005. Irony as persuasive communication. In H. Colston and A. Katz, editors, Figurative language comprehension: Social and cultural influences, pages 131–151. Lawrence Erlbaum, New York, NY. find
  13. R. W. Gibbs and J. O’Brien. 1991. Psychological aspects of irony understanding. Journal of pragmatics, 16(6):523–530. find
  14. R. W. Gibbs. 1986. On the psycholinguistics of sarcasm. Journal of Experimental Psychology: General, 115(1):3. find
  15. R. W. Gibbs. 2007. On the psycholinguistics of sarcasm. In R. W. Gibbs, R. W. Gibbs Jr., and H. Colston, editors, Irony in language and thougt: A cognitive science reader, pages 173–200. Lawrence Erlbaum, New York, NY. find
  16. R. Giora, O. Fein, J. Ganzi, N. Levi, and H. Sabah. 2005. On negation as mitigation: the case of negative irony. Discourse Processes, 39(1):81–100. find
  17. R. Giora. 1995. On irony and negation. Discourse processes, 19(2):239–264. find
  18. R. Giora. 2003. On our mind: Salience, context, and figurative language. Oxford University Press. find
  19. C. Goddard. 2006. ”lift your game Martina!”: Deadpan jocular irony and the ethnopragmatics of Australian English. APPLICATIONS OF COGNITIVE LINGUISTICS, 3:65. find
  20. H. Grice. 1975. Logic and conversation. In P. Cole and J. Morgan, editors, Speech acts: Syntax and semantics, pages 41–58. Academic Press, New York, NY. find
  21. H. Grice. 1978. Further notes on logic and conversation. In P. Cole, editor, Pragmatics: syntax and semantics, pages 113–127. Academic Press, New York, NY. find
  22. H. Hamamoto. 1998. Irony from a cognitive perspective. In R. Carston and S. Uchida, editors, Relevance theory: Applications and implications, pages 257–270. John Benjamins, Amsterdam, The Netherlands. find
  23. K. Jahandarie. 1999. Spoken and written discourse: A multi-disciplinary perspective. Greenwood Publishing Group. find
  24. H. Kotthoff. 2003. Responding to irony in different contexts: On cognition in conversation. Journal of Pragmatics, 35(9):1387–1411. find
  25. R. J. Kreuz and R. M. Roberts. 1993. The empirical study of figurative language in literature. Poetics, 22(1):151–169. find
  26. R. J. Kreuz and R. M. Roberts. 1995. Two cues for verbal irony: Hyperbole and the ironic tone of voice. Metaphor and symbol, 10(1):21–31. find
  27. R. Kreuz, R. Roberts, B. Johnson, and E. Bertus. 1996. Figurative language occurrence and co-occurrence in contemporary literature. In R. Kreuz and M. Mac-Nealy, editors, Empirical approaches to literature and aesthetics, pages 83–97. Ablex, Norwood, NJ. find
  28. J. H Leigh. 1994. The use of figures of speech in print ad headlines. Journal of Advertising, pages 17–33. find
  29. N. Littlestone. 1988. Learning quickly when irrelevant attributes abound: A new linear-threshold algorithm. Machine Learning, 2:285–318. find
  30. Z. Livnat. 2004. On verbal irony, meta-linguistic knowledge and echoic interpretation. Pragmatics & Cognition, 12(1):57–70. find
  31. M. Mizzau. 1984. L’ironia: la contraddizione consen-tita. Feltrinelli, Milan, Italy. find
  32. A. Montoyo, P. Martı́nez-Barco, and A. Balahur. 2012. Subjectivity and sentiment analysis: An overview of the current state of the area and envisaged developments. Decision Support Systems. find
  33. R. Morante and W. Daelemans. 2009. Learning the scope of hedge cues in biomedical texts. In Proceedings of the Workshop on BioNLP, pages 28–36. Association for Computational Linguistics. find our card
  34. R. Morante, A. Liekens, and W. Daelemans. 2008. Learning the scope of negation in biomedical texts. In Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing, pages 715– 724. find
  35. D. C. Muecke. 1969. The compass of irony. Oxford Univ Press. find
  36. D. C. Muecke. 1978. Irony markers. Poetics, 7(4):363– 375. find
  37. A. Partington. 2007. Irony and reversal of evaluation. Journal of Pragmatics, 39(9):1547–1569. find
  38. A. Reyes, P. Rosso, and D. Buscaldi. 2012a. From humor recognition to irony detection: The figurative language of social media. Data & Knowledge Engineering. find
  39. A. Reyes, P. Rosso, and T. Veale. 2012b. A multidimensional approach for detecting irony in twitter. Language Resources and Evaluation, pages 1–30. find
  40. P. Rockwell. 2003. Empathy and the expression and recognition of sarcasm by close relations or strangers. Perceptual and motor skills, 97(1):251–256. find
  41. P. Rockwell. 2007. Vocal features of conversational sarcasm: A comparison of methods. Journal of psycholinguistic research, 36(5):361–369. find
  42. K.-i. Seto. 1998. On non-echoic irony. In R. Carson and S. Uchida, editors, Relevance theory: Applications and implications, pages 239–255. John Benjamins, Amsterdam, The Netherlands. find
  43. S. Siegel and N. Castellan. 1988. Nonparametric statistics for the behavioral sciences. McGraw Hill, New York. find
  44. D. Sperber and D. Wilson. 1995. Relevance: Communication and cognition. Blackwell Publishers, Oxford, UK, 2nd edition. find
  45. D. Srinarawat. 2005. Indirectness as a politeness strategy of Thai speakers. In R. Lakoff and S. Ide, editors, Broadening the horizon of linguistic politeness, pages 175–193. John Benjamins, Amsterdam, The Netherlands. find
  46. O. Tsur, D. Davidov, and A. Rappoport. 2010. Icwsm– a great catchy name: Semi-supervised recognition of sarcastic sentences in online product reviews. In Proceedings of the Fourth International AAAI Conference on Weblogs and Social Media, pages 162–169. find
  47. M. Van Mulken and P. J. Schellens. 2012. Over lood-zware bassen en wapperende broekspijpen. gebruik en perceptie van taalintensiverende stijlmiddelen. Tijdschrift voor taalbeheersing, 34(1):26–53. find